{"id":"W6979255877","doi":"","title":"Evaluating Multi-Hop Reasoning in Large Language Models: A Chemistry-Centric Case Study","year":2025,"lang":"en","type":"article","venue":"ArXiv.org","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Mitacs","keywords":"Pipeline (software); Context (archaeology); Benchmark (surveying); Automated reasoning; Process (computing); Case-based reasoning; Model-based reasoning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003567177,0.0002432079,0.0003361153,0.0001295595,0.000311669,0.0001598943,0.0005596336,0.00008396243,0.0006313953],"category_scores_gemma":[0.00178098,0.0002296825,0.00004565731,0.0007416233,0.00006194226,0.000323587,0.0004998647,0.000283312,0.0001368908],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001541383,"about_ca_system_score_gemma":0.0001421264,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00203588,"about_ca_topic_score_gemma":0.0003545634,"domain_scores_codex":[0.9972159,0.000461034,0.0005252868,0.0007758344,0.0003737428,0.0006482102],"domain_scores_gemma":[0.9988005,0.0001770766,0.0001909806,0.0006532601,0.00009069787,0.00008746273],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002420175,0.0004378685,0.3924955,0.00007549454,0.000005522565,0.001301436,0.005796866,0.00948712,0.5901098,0.00001878573,0.00001282027,0.0002345643],"study_design_scores_gemma":[0.005123517,0.0001402592,0.07710832,0.0003665245,0.000071863,0.0003404187,0.02333075,0.8137514,0.0789137,0.00004931741,0.00003209979,0.0007718041],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9966407,0.0001707908,0.00154608,0.0000564064,0.0003562821,0.0004949925,0.000008904814,0.0001977579,0.0005281148],"genre_scores_gemma":[0.9935539,0.000002495747,0.005320737,0.0001179915,0.00005933813,0.00008270024,0.000003580693,0.00002164138,0.0008375799],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8042643,"threshold_uncertainty_score":0.936618,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05388192935518151,"score_gpt":0.3765414905720963,"score_spread":0.3226595612169149,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}